© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15583
    Prev
    Next
    INDEX
    Explanations

    evaluating sensory experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    218
    -0.12
     devant
    -0.11
     sounded
    -0.11
    akov
    -0.11
    ogan
    -0.11
     dol
    -0.10
    ehen
    -0.10
     happily
    -0.10
     confidently
    -0.10
     Gim
    -0.10
    POSITIVE LOGITS
     wonderful
    0.09
     unnatural
    0.09
     nice
    0.09
     better
    0.09
     like
    0.08
     strange
    0.08
     sinful
    0.08
    ...
    0.08
    ----
    0.08
     wrong
    0.07
    Activations Density 0.005%

    No Known Activations